본문으로 건너뛰기
cccskills
무료GitHub에 공개

toon

Convert data to/from TOON (Token-Oriented Object Notation) for lower-token LLM context. Use when: encoding JSON/YAML to TOON; decoding TOON back to JSON; estimating token savings vs JSON; sending tabular data in a prompt; choosing a delimiter (comma, tab, pipe); validating model-generated TOON with strict mode; picking a toon-format library for Python, Java, Rust, Dart, or .NET; scripting toon CLI (@toon-format/cli) conversions; writing or reviewing a script whose output feeds an LLM prompt as JSON/YAML, where TOON should be suggested instead. Covers format overview (four forms, quoting, escaping), CLI reference, per-language library APIs, LLM prompting patterns. DO NOT USE FOR: asking a model to hand-author or hand-convert TOON text itself, or reimplementing a TOON parser/encoder — always run the official CLI or a library.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics스타 36(GitHub 36 + cccskills 0)

실행 점수 미검증

설치 방법 보기

포함된 파일(4)

  • SKILL.md5.0 KB
  • references/cli-and-libraries.md5.0 KB
  • references/format-spec.md3.9 KB
  • references/llm-integration-patterns.md3.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

TOON

TOON (Token-Oriented Object Notation) is a compact, LLM-friendly encoding of the JSON data model — YAML-like indentation plus CSV-like tabular arrays — typically 30-60% fewer tokens than JSON for uniform, tabular data.

Anatomy

FilePurposeTarget Size
SKILL.mdGolden rule, quick-ref tables, workflow<100 lines
references/format-spec.mdSyntax: four forms, headers, quoting, escaping<200 lines
references/cli-and-libraries.md@toon-format/cli + Python/Java/Rust/Dart/.NET libraries<200 lines
references/llm-integration-patterns.mdPrompting with TOON input, strict-mode validation<200 lines

Golden Rule: Never Hand-Convert or Hand-Parse

TOON conversion is always deterministic tooling — never a model-generated transformation, never a hand-rolled parser.

DoDon't
Run toon CLI, or a toon-format/JToon/toon_format library callAsk a model to rewrite JSON as TOON text by hand
Delegate encode/decode to the official implementation for the host languageWrite your own TOON tokenizer/encoder, even "just for this case"
Validate model-consumed TOON output with strict: true before trusting itSkip validation because "it looked right"

Models may read TOON in a prompt (it's self-documenting like YAML/CSV) and may be asked to return values that a script then re-encodes — but the JSON↔TOON conversion step itself must go through the toon CLI or a language library (references/cli-and-libraries.md), never free-form generation.

Proactively Suggest TOON

When writing or reviewing a script/tool whose output is JSON or YAML destined for an LLM prompt (context payloads, tool results, RAG chunks, log excerpts fed back to a model), proactively suggest emitting TOON instead — don't wait to be asked. Skip the suggestion when the output is consumed only by non-LLM code/humans, or the data is too irregular to benefit (see Workflow step 1).

Quick Reference

# CLI (no install): encode JSON -> TOON, show token savings
npx @toon-format/cli data.json --stats -o data.toon
npx @toon-format/cli data.toon -o data.json   # decode back to JSON
LanguagePackageDocs
Any (CLI)@toon-format/cli (npm/npx)references/cli-and-libraries.md
Pythontoon-format (PyPI)references/cli-and-libraries.md
Javadev.toonformat:jtoon (Maven Central)references/cli-and-libraries.md
Rusttoon-format (crates.io)references/cli-and-libraries.md
.NETToon.Format (NuGet)references/cli-and-libraries.md
Darttoon_format (pub.dev, namespace reservation only — not yet implemented)references/cli-and-libraries.md

Workflow

  1. Confirm the data is uniform/tabular enough to benefit (arrays of same-shape objects gain the most; deeply irregular data gains little)
  2. Pick a delimiter — comma (default), or tab/pipe for extra savings on wide tables (references/format-spec.md)
  3. Encode via the CLI or a native library (references/cli-and-libraries.md) — never by hand
  4. Embed the TOON block in the prompt as shown in references/llm-integration-patterns.md
  5. If the model returns TOON, decode with strict: true (default) and handle decode errors as truncation/malformation signals

Reference Files

FileLoad When
references/format-spec.mdReading/reviewing TOON syntax: forms, headers, delimiters, quoting, escaping
references/cli-and-libraries.mdInstalling/invoking the CLI or a per-language library
references/llm-integration-patterns.mdEmbedding TOON in prompts, streaming, validating model output

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

3d-rotation-theory

무료

Abstract math for 3D rotation representations and conversions. USE FOR: understanding axis-angle representation; Euler angles (yaw/pitch/roll, convention choices); rotation matrices (SO(3)); quaternion-based rotation; converting between representations; identifying and avoiding gimbal lock; composing rotations; half-angle formula; right-hand rule. DO NOT USE FOR: quaternion arithmetic details (use quaternion-algebra); slerp/lerp interpolation (use interpolation-on-manifolds); coordinate system definitions (use coordinate-system-conversions).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics362026년 8월 10일 업데이트

agent-graph-orchestration

무료

Design and scaffold multi-agent squads/swarms using the graph orchestration pattern (nodes = agents, edges = dependencies/data flow). USE FOR: designing a coordination topology for a multi-agent squad (sequential pipeline, parallel fan-out/aggregation, branching, feedback loop, cyclic); building an orchestrator agent that delegates to specialist agents; setting up an adversarial/tribunal code or document review with independent reviewers; scaffolding a squad's agent files for a target coding-agent harness (e.g. Copilot CLI or Claude Code custom agents). DO NOT USE FOR: authoring a single agent's frontmatter/prompt body (use copilot-cli-custom-agents, claude-code-custom-agents, or the target harness's own skill); SKILL.md authoring (use create-skill); ad-hoc multi-agent chat with no explicit topology.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics362026년 8월 10일 업데이트

agent-harness-logs

무료

Find, inspect, query, redact, and troubleshoot logs, transcripts, sessions, and OpenTelemetry data from coding-agent harnesses on Windows, macOS, Linux, and WSL. USE FOR: GitHub Copilot in VS Code; Copilot CLI; Claude Code; OpenAI Codex; Gemini CLI; OpenCode; Cursor, Windsurf, Kiro, or other VS Code-family editors; locating log files; diagnosing tool or model failures; correlating turns, subagents, and tool calls; querying JSONL, plaintext, or SQLite without spending model tokens; preparing sanitized diagnostics. DO NOT USE FOR: application logs unrelated to coding agents; uploading raw logs; treating unstable transcript schemas as public APIs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics362026년 8월 10일 업데이트

agents-md

무료

Author and maintain AGENTS.md files — the open, tool-agnostic format for giving coding agents project context. Use when: creating AGENTS.md; writing an agent instructions file; root or nested AGENTS.md for monorepos; migrating CLAUDE.md, AGENT.md, .cursor/rules, or copilot-instructions.md to AGENTS.md; greenfield project setup before code exists; brownfield onboarding for an existing codebase; documenting build/test/lint commands, code style, PR/commit conventions, and security considerations for agents; AGENTS.md discovery and precedence rules. Works for any language, framework, or project size. DO NOT USE FOR: authoring SKILL.md skill files (use create-skill); APM package/plugin authoring (use apm-producer); language-specific style rules (use language skills e.g. csharp-best-practices).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics362026년 8월 10일 업데이트

angles-and-circular-arithmetic

무료

Abstract math for angle measurement, unit systems, and circular arithmetic. USE FOR: implementing angle types; converting between degrees/radians/gradians/revolutions; reducing angles to canonical range [0, Full); computing reference angles and quadrants; implementing safe modular arithmetic with negative inputs; angle addition and subtraction; classifying angles by sign and size. DO NOT USE FOR: trigonometric functions (use trigonometric-functions); coordinate conversions (use coordinate-system-conversions); interpolation (use interpolation-on-manifolds).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics362026년 8월 10일 업데이트

claude-code-custom-agents

무료

Create and maintain Claude Code custom subagents (.claude/agents/*.md files). USE FOR: authoring project (.claude/agents/) or user (~/.claude/agents/) subagent files; frontmatter fields (name, description, tools, disallowedTools, model, permissionMode, maxTurns, skills, mcpServers, hooks, memory, background, effort, isolation, color, initialPrompt); writing descriptions that drive automatic delegation and 'use proactively' phrasing; invoking subagents via natural language, @-mention, session-wide --agent, or the Agent tool; restricting which subagent types a coordinator can spawn with Agent(name1, name2); nested subagents and depth limits; built-in subagents (Explore, Plan, general-purpose, claude); troubleshooting a subagent that won't load or isn't invoked. DO NOT USE FOR: GitHub Copilot CLI custom agents (use copilot-cli-custom-agents); agent teams/teammates (a different, session-spanning feature); MCP server authoring; SKILL.md authoring (use create-skill).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NetFabric/NetFabric.Numerics362026년 8월 10일 업데이트

NetFabric의 스킬 모두 보기

이 스킬의 문제 신고